© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 5504
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `sorted` keyword or `len` function argument (negative activations)

    python-code · gemini-2.5-flash-lite

    attribute access in class methods

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _edges
    -0.02
     next
    -0.02
     found
    -0.02
    ist
    -0.02
     e
    -0.01
     f
    -0.01
     output
    -0.01
     not
    -0.01
    ver
    -0.01
    test
    -0.00
    POSITIVE LOGITS
    _grid
    0.04
    structions
    0.03
     grid
    0.02
    adj
    0.02
    grid
    0.02
    A
    0.02
     w
    0.01
    '
    0.00
    #
    0.00
    &
    0.00
    Activations Density 99.776%

    No Known Activations